STAR：基于扩散的光场重建的结构感知测试时自适应
STAR: Structure-aware Test-time Adaptation for diffusion-based light field Reconstruction
浏览论文内容
中文总结 AI 辅助
STAR提出首个测试时自适应框架，通过冻结扩散先验并拟合三个轻量适配器，联合自适应光场空间-角度结构，在双/三焦面重建中超越现有方法且推理更快。
中文摘要 AI 辅助
从有限且含噪的焦栈（FS）测量中重建光场（LF）是一个高度不适定的逆问题。尽管对于给定的光学设置，LF到FS的成像几何是固定的，但LF的空间-角度结构——包括视图内的空间细节、视图间的角度依赖以及视图间的视差——在不同场景中会有所变化。因此，固定的预训练先验可能无法最优地捕捉每个测试LF的空间-角度结构。我们提出了STAR（Structure-aware Test-time Adaptation for diffusion-based light field Reconstruction），这是首个用于从FS重建LF的测试时自适应框架。对于每个测试LF，STAR冻结预训练的扩散先验，并拟合三个轻量级适配器到观测的FS，以联合自适应LF空间-角度结构的三个组成部分。STAR在双焦面和三焦面设置下均优于现有最先进方法，且推理时间短于具有测试时参数更新的方法。
英文摘要
Light field (LF) reconstruction from limited and noisy focal stack (FS) measurements is a highly ill-posed inverse problem. Although the LF-to-FS imaging geometry is fixed for a given optical setup, LF spatial-angular structure---including within-view spatial details, cross-view angular dependencies, and disparity across views---varies across scenes. Consequently, a fixed pre-trained prior may not optimally capture the spatial-angular structure of each test LF. We propose Structure-aware Test-time Adaptation for diffusion-based light field Reconstruction (STAR), the first test-time adaptation framework for reconstructing an LF from FS. For each test LF, STAR freezes a pre-trained diffusion prior and fits three lightweight adapters to the observed FS to jointly adapt the three components of the LF's spatial-angular structure. STAR outperforms existing state-of-the-art methods in both two- and three-focal-sheet settings, with shorter inference times than those with test-time parameter updates.
发表机构
- Sungkyunkwan University (SKKU)（成均馆大学）
机构由 AI 辅助整理，请以论文原文为准。
